arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2009.06141cs.CLcs.AIcs.IR
收藏

阅读理解中的多段式答题

Composing Answer from Multi-spans for Reading Comprehension

Zhuosheng Zhang, Yiqing Zhang, Hai Zhao, Xi Zhou, Xiang Zhou

摘要:

针对非抽取式机器阅读理解(MRC)问题,提出了一种新的答案生成方法。当地面实况答案由人类注释者给出或从部分段落高度重新释义时,针对这种类型的MRC使用指针网络式提取解码器可能导致不令人满意的性能。另一方面,当遇到长句时,使用生成式解码器不能很好地保证结果具有良好的语法和语义。因此,为了减轻双方的明显缺点,我们提出了一个答案弥补方法,从提取的多跨度,我们的模型学习作为高度自信的$n$ -gram候选人在给定的通道。也就是说,返回的答案是由不连续的多个跨度组成的,而不仅仅是给定段落中的一个连续的跨度。该方法简单有效:在MS MARCO上的实验表明,该方法在准确生成长答案方面具有更好的性能,并大大优于两种典型的单跨度和Seq 2Seq基线解码器。

英文摘要:

This paper presents a novel method to generate answers for non-extraction machine reading comprehension (MRC) tasks whose answers cannot be simply extracted as one span from the given passages. Using a pointer network-style extractive decoder for such type of MRC may result in unsatisfactory performance when the ground-truth answers are given by human annotators or highly re-paraphrased from parts of the passages. On the other hand, using generative decoder cannot well guarantee the resulted answers with well-formed syntax and semantics when encountering long sentences. Therefore, to alleviate the obvious drawbacks of both sides, we propose an answer making-up method from extracted multi-spans that are learned by our model as highly confident $n$-gram candidates in the given passage. That is, the returned answers are composed of discontinuous multi-spans but not just one consecutive span in the given passages anymore. The proposed method is simple but effective: empirical experiments on MS MARCO show that the proposed method has a better performance on accurately generating long answers, and substantially outperforms two competitive typical one-span and Seq2Seq baseline decoders.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑